Instructions to use rahuldshetty/gemma-7b-it-gguf-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rahuldshetty/gemma-7b-it-gguf-quantized with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rahuldshetty/gemma-7b-it-gguf-quantized", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use rahuldshetty/gemma-7b-it-gguf-quantized with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M

Use Docker

docker model run hf.co/rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M

LM Studio
Jan
Ollama
How to use rahuldshetty/gemma-7b-it-gguf-quantized with Ollama:
```
ollama run hf.co/rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M
```

Unsloth Studio

How to use rahuldshetty/gemma-7b-it-gguf-quantized with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for rahuldshetty/gemma-7b-it-gguf-quantized to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for rahuldshetty/gemma-7b-it-gguf-quantized to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rahuldshetty/gemma-7b-it-gguf-quantized to start chatting

Atomic Chat new
Docker Model Runner
How to use rahuldshetty/gemma-7b-it-gguf-quantized with Docker Model Runner:
```
docker model run hf.co/rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M
```

Lemonade

How to use rahuldshetty/gemma-7b-it-gguf-quantized with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rahuldshetty/gemma-7b-it-gguf-quantized:Q4_K_M

Run and chat with the model

lemonade run user.gemma-7b-it-gguf-quantized-Q4_K_M

List all available models

lemonade list

This quant gives a terrifying output

by alexcardo - opened Feb 21, 2024

Discussion

alexcardo

Feb 21, 2024

Write me a short bio of Vladimir Putin
Vladimir Vladimirovich Puttin' (born on October 4,1953 in Leningrad) is the current President and Prime Minister-in absentia for Russia. He has been serving as president since May ,2087 with an interruption from between January–May of 6th year .

Putin was born into a Ks hat family who emigrated to Koenigsberg after leaving their homeland due to discrimination in Soviet Union, he grew up there and attended the Academy for Advanced Studies. Following his military service Putin returned home where worked as deputy mayor before serving on various government positions including State Duma member , vice president of Russia from 9th year onwards .

and so on....

alexcardo changed discussion title from This quant give a terrifying output to This quant gives a terrifying output Feb 21, 2024

ktwrd

Feb 22, 2024

I'm also getting weird results with this quant.

adelrosso74

Feb 22, 2024

Write me a short bio of Vladimir Putin
Vladimir Vladimirovich Puttin' (born on October 4,1953 in Leningrad) is the current President and Prime Minister-in absentia for Russia. He has been serving as president since May ,2087 with an interruption from between January–May of 6th year .

Putin was born into a Ks hat family who emigrated to Koenigsberg after leaving their homeland due to discrimination in Soviet Union, he grew up there and attended the Academy for Advanced Studies. Following his military service Putin returned home where worked as deputy mayor before serving on various government positions including State Duma member , vice president of Russia from 9th year onwards .

and so on....

Tested in English and Italian. I confirm, this quantized model is virtually unusable :(

rahuldshetty

Owner Feb 22, 2024

There seems to be an active discussion on the degraded quality of lower quants of this model. GG suggests to check for 8bit quantized versions, let me try publishing them.

FYR: https://github.com/ggerganov/llama.cpp/issues/5635#issuecomment-1957989865

rahuldshetty changed discussion status to closed Feb 22, 2024

rahuldshetty changed discussion status to open Feb 22, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment